SoK: Federated Learning for Intrusion Detection in Vehicular Networks

2026-07-12

AI Summary

This work addresses the fragmented methodologies and unrealistic experimental setups prevalent in current vehicular federated learning-based intrusion detection systems (FL-IDS), which hinder real-world deployment. Employing a Systematization of Knowledge (SoK) approach, it establishes the first unified taxonomy for vehicular FL-IDS, systematically characterizing attack surfaces, evaluating federated topologies, and mapping adversarial threats such as poisoning and inference attacks. Through an audit of over 60 studies, the analysis uncovers common shortcomings—including overly idealized IID data assumptions, oversimplified benchmarks, and insufficient adversarial evaluation—and proposes minimal baseline requirements tailored for practical deployment. The study thus delivers a standardized evaluation framework and outlines a clear research roadmap toward secure and deployable vehicular FL-IDS solutions.

Abstract

Modern vehicular networks face an expanding attack surface across internal Electronic Control Units (ECUs) and external Vehicle-to-Everything (V2X) communication. Federated Learning (FL) has emerged as a decentralized paradigm to deploy Intrusion Detection Systems (IDS) without compromising data privacy. However, the vehicular FL-IDS literature suffers from fragmented methodologies and unrealistic experimental setups. This paper presents a Systematization of Knowledge (SoK) that unifies the taxonomy of vehicular attack surfaces, evaluates FL topologies, and maps adversarial threats such as poisoning and inference attacks. By auditing over 60 publications, we identify recurring pitfalls: artificial IID data splits, reliance on trivial benchmarks, weak adversarial evaluation, and omission of real-time CAN constraints. Finally, we define a forward-looking research agenda and outline minimum benchmarking requirements necessary to transition vehicular FL-IDS from optimistic simulations to secure, real-world deployment.

Problem

• Federated Learning
• Intrusion Detection
• Vehicular Networks
• Adversarial Threats
• Systematization of Knowledge

Innovation

• Federated Learning
• Intrusion Detection System
• Vehicular Networks
• Adversarial Attacks
• Systematization of Knowledge